© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4067
    Prev
    Next
    INDEX
    Explanations

    food, festivals, seafood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ½åĩº
    -0.10
    trail
    -0.09
    гоÑĢод
    -0.09
    åĸĿæ°´
    -0.09
    æĢĽ
    -0.09
    raid
    -0.09
    æ°ijæĶ¿
    -0.09
    Seeder
    -0.09
    ÑĢе
    -0.09
    ç§įåŃIJ
    -0.09
    POSITIVE LOGITS
     seafood
    0.15
    æµ·é²ľ
    0.15
    é±¼
    0.12
    éŃļ
    0.12
    鱼类
    0.11
     fish
    0.11
     shrimp
    0.11
    饵
    0.11
     Fish
    0.11
     fishermen
    0.10
    Activations Density 0.143%

    No Known Activations